%0 Conference Paper %1 Kawai2004 %A Kawai, Hisashi %A Toda, Tomoki %A Ni, Jinfu %A Tsuzaki, Minoru %A Tokuda, Keiichi %B Proceedings of the 5th ISCA Workshop on Speech Synthesis (SSW) %C Pittsburgh, PA, USA %D 2004 %K imported %P 179-184 %T XIMERA: A New TTS from ATR Based on Corpus-Based Technologies %U http://www.isca-speech.org/archive_open/ssw5/ssw5_179.html %X This paper describes a new concatenative TTS system under development at ATR. The system, named XIMERA, is based on corpus-based technologies, as was the case for the preceding TTS systems from ATR, namely ν-talk and CHATR. The prominent features of XIMERA are (1) large corpora (a 110-hours corpus of a Japanese male, a 60-hours corpus of a Japanese female, and a 20-hours corpus of a Chinese female), (2) HMM-based generation of prosodic parameters, and (3) a cost function for segment selection optimized based on perceptual experiments. A perception test that evaluated the naturalness of synthetic speech for XIMERA and 10 TTS products, including CHATR, showed that XIMERA outperformed the other ten.

@inproceedings{Kawai2004, abstract = {This paper describes a new concatenative TTS system under development at ATR. The system, named XIMERA, is based on corpus-based technologies, as was the case for the preceding TTS systems from ATR, namely ν-talk and CHATR. The prominent features of XIMERA are (1) large corpora (a 110-hours corpus of a Japanese male, a 60-hours corpus of a Japanese female, and a 20-hours corpus of a Chinese female), (2) HMM-based generation of prosodic parameters, and (3) a cost function for segment selection optimized based on perceptual experiments. A perception test that evaluated the naturalness of synthetic speech for XIMERA and 10 TTS products, including CHATR, showed that XIMERA outperformed the other ten.}, added-at = {2021-02-01T10:51:23.000+0100}, address = {Pittsburgh, PA, USA}, author = {Kawai, Hisashi and Toda, Tomoki and Ni, Jinfu and Tsuzaki, Minoru and Tokuda, Keiichi}, biburl = {https://www.bibsonomy.org/bibtex/23454670452bd464531909c0c6809f6f3/m-toman}, booktitle = {Proceedings of the 5th ISCA Workshop on Speech Synthesis (SSW)}, file = {:pdfs/kawai_ssw_2004.pdf:PDF}, interhash = {f506028d47618de58dcad34d5c84c853}, intrahash = {3454670452bd464531909c0c6809f6f3}, keywords = {imported}, month = jun, owner = {schabus}, pages = {179-184}, timestamp = {2021-02-01T10:51:23.000+0100}, title = {XIMERA: A New TTS from ATR Based on Corpus-Based Technologies}, url = {http://www.isca-speech.org/archive_open/ssw5/ssw5_179.html}, year = 2004 }